CN102657533A - Falling detection method, falling detection device and wrist type device - Google Patents
Falling detection method, falling detection device and wrist type device Download PDFInfo
- Publication number
- CN102657533A CN102657533A CN2012101334477A CN201210133447A CN102657533A CN 102657533 A CN102657533 A CN 102657533A CN 2012101334477 A CN2012101334477 A CN 2012101334477A CN 201210133447 A CN201210133447 A CN 201210133447A CN 102657533 A CN102657533 A CN 102657533A
- Authority
- CN
- China
- Prior art keywords
- comprehensive
- less
- threshold
- velocity amplitude
- setting threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 210000000707 wrist Anatomy 0.000 title claims abstract description 12
- 230000001133 acceleration Effects 0.000 claims abstract description 57
- 230000010354 integration Effects 0.000 claims description 27
- 238000001914 filtration Methods 0.000 claims description 18
- 238000009825 accumulation Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 13
- 230000003068 static effect Effects 0.000 claims description 8
- 230000033001 locomotion Effects 0.000 abstract description 5
- 230000036541 health Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 230000005484 gravity Effects 0.000 description 4
- 210000004247 hand Anatomy 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 208000031872 Body Remains Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 210000001217 buttock Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a falling detection method, a falling detection device and a wrist type device. The falling detection device disclosed by the embodiment of the invention comprises a triaxial acceleration sensor, a vertical motion speed value and non-rotation state speed value acquisition module, a first judgment module, a second judgment module, a third judgment module, an angle deviation acquisition module and a fourth judgment module. According to the falling detection device disclosed by the invention, the acceleration sensor is adopted for setting different threshold standards according to different people groups, so that falling with different strengths can be detected, serious consequences caused by falling can be avoided, and the falling detection device is simple and convenient to use.
Description
Technical field
The invention belongs to the detection technique field, relate to a kind of fall detection method, fall detection device and wrist formula equipment especially.
Background technology
The development of Along with computer technology, wireless communication technology and medical skill, society steps into the electronic health care epoch gradually.Get into 21 century, the electronic health care plan is also being included in the reform of domestic medical and health system in.Electronic health care is information technology omnibearing application in the health care field, is the of paramount importance revolution in health care of modern medicine health.Along with the continuous development of wired, wireless messages network infrastructure and terminal unit, perfect, in the near future, people can enjoy health service anywhere or anytime.
The research center result of China shows in the recent period, and the China's old people proportion of 65 years old old people's proportion above 7%, 60 years old surpassed 10%.These data show China and are just progressively marched toward the aging epoch.Along with the increase of social work pressure, the busy children of many work can't take into account the health status that the old people is in.Along with the increase at age, the decline of function of human body, the old people often falls easily, and it is preceding ten in old people's unexpected injury seniority among brothers and sisters to fall, and if do not have the guardian tend to cause the result's generation that can not estimate at one's side in the back of falling.
For accuracy and the Algorithm design that improves detection, domestic and international most of fall detection equipment all is based on position exploitation that difficult generation strong movements such as place, chest changes, and the fall detection of wrist position Wearable is very rare.
So; To the above-mentioned defective that exists in the present prior art, be necessary to study in fact, so that a kind of scheme to be provided; Solve the defective that exists in the prior art; Be used for setting different threshold criteria and can detect varying strength and fall, avoid causing serious consequence because fall according to different crowds, simple and convenient.
Summary of the invention
For addressing the above problem, the object of the present invention is to provide a kind of fall detection method, fall detection device and wrist formula equipment, be used for based on the real-time accekeration of sensor human body, simple, high-accuracy ground judges whether human body falls.
For realizing above-mentioned purpose, technical scheme of the present invention is:
A kind of fall detection method may further comprise the steps:
Step 10; Obtain the corresponding 3-axis acceleration analogue signal of human body from 3-axis acceleration sensor; Use peaceful filtering of the filtering algorithm Chinese and moving average method to carry out filtering and reduce the violent error deviation of moment that noise produces; The 3-axis acceleration digital signal that obtains is changed into comprehensive accekeration, get into step 20;
Step 20 utilizes the comprehensive accekeration obtain that the static original state of gravitational cue is calibrated, and utilizes integration to obtain to move both vertically velocity amplitude and non-rotating state velocity amplitude, entering step 30;
Whether step 30, the instant value of judging said comprehensive accekeration less than setting threshold,
If be not less than setting threshold, return and continue step 10,
If less than setting threshold, accumulation calculating non-rotating state velocity amplitude and said integration obtain the difference of the velocity amplitude that moves both vertically, and the moment point of the conditional judgment of falling is basically satisfied in the zero-time representative of integration, stop moment representative and add up the finish time, get into step 40;
Whether step 40 judges difference that said accumulation calculating non-rotating state velocity amplitude and said integration obtain the velocity amplitude that moves both vertically less than setting threshold,
If less than setting threshold, return and continue step 10,
If be not less than setting threshold, the difference of comprehensive accekeration of accumulation calculating and comprehensive acceleration of last moment identifies as exercise intensity, gets into step 50;
Whether step 50, the difference of judging the last comprehensive accekeration and comprehensive acceleration of last moment greater than setting threshold,
If greater than setting threshold, return and continue step 10,
If less than setting threshold, whether detect the exercise intensity sign greater than setting threshold, if less than setting threshold, get into step 60;
Whether step 70 judges the unspecified angle skew that calculates greater than the setting offset threshold,
If greater than setting offset threshold, return and continue step 10,
If less than setting offset threshold, do not exist three angles simultaneously less than the moment of threshold value and do not have comprehensive accekeration in the cycle time very first time with the difference of comprehensive acceleration of last moment is not more than its threshold value, the judgement human body is fallen.
A kind of fall detection device comprises 3-axis acceleration sensor, move both vertically velocity amplitude and non-rotating state velocity amplitude acquisition module, first judge module, second judge module, the 3rd judge module, angular deflection acquisition module and the 4th judge module,
Said 3-axis acceleration sensor is used to obtain the corresponding 3-axis acceleration analogue signal of human body; Use peaceful filtering of the filtering algorithm Chinese and moving average method to carry out filtering and reduce the violent error deviation of moment that noise produces, the 3-axis acceleration digital signal that obtains is changed into comprehensive accekeration;
Said velocity amplitude and the non-rotating state velocity amplitude acquisition module of moving both vertically is used to utilize the comprehensive accekeration that obtains that the static original state of gravitational cue is calibrated, and utilizes integration to obtain to move both vertically velocity amplitude and non-rotating state velocity amplitude;
Whether the instant value that said first judge module is used to judge said comprehensive accekeration less than setting threshold,
If be not less than setting threshold, return and continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If less than setting threshold, accumulation calculating non-rotating state velocity amplitude and said integration obtain the difference of the velocity amplitude that moves both vertically, and the moment point of the conditional judgment of falling is basically satisfied in the zero-time representative of integration, and stopping constantly, representative adds up the finish time;
Whether said second judge module is used to judge difference that said accumulation calculating non-rotating state velocity amplitude and said integration obtain the velocity amplitude that moves both vertically less than setting threshold,
If less than setting threshold, return and continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If be not less than setting threshold, the difference of comprehensive accekeration of accumulation calculating and comprehensive acceleration of last moment identifies as exercise intensity;
Whether said the 3rd judge module is used to judge the difference of the last comprehensive accekeration and comprehensive acceleration of last moment greater than setting threshold,
If greater than setting threshold, continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If less than setting threshold, whether detect the exercise intensity sign greater than setting threshold;
Said angular deflection acquisition module is used to calculate three angular deflection
Whether said the 4th judge module is used to judge the unspecified angle skew that calculates greater than the setting offset threshold,
If continue to obtain the corresponding 3-axis acceleration analogue signal of human body greater than setting offset threshold, returning,
If less than setting offset threshold, do not exist three angles simultaneously less than the moment of threshold value and do not have comprehensive accekeration in the cycle time very first time with the difference of comprehensive acceleration of last moment is not more than its threshold value, the judgement human body is fallen.
A kind of wrist formula equipment is worn on the human body wrist place, it is characterized in that, comprises above-mentioned fall detection device.
With prior art adopt based on the image/video monitoring, compare based on Acoustic detection or based on the implementation that the infrared detection human body is fallen; The present invention adopts acceleration transducer to be used for setting different threshold criteria according to different crowds and can detect varying strength and fall; Avoid causing serious consequence because fall, simple and convenient.
Description of drawings
Fig. 1 is the fall detection method flow diagram of the embodiment of the invention;
Fig. 2 is the signal schematic representation of falling of the fall detection method of the embodiment of the invention;
Fig. 3 is the fall detection apparatus structure sketch map of the embodiment of the invention.
The specific embodiment
In order to make the object of the invention, technical scheme and advantage clearer,, the present invention is further elaborated below in conjunction with accompanying drawing and embodiment.Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
On the contrary, any alternative, the modification of on marrow of the present invention and scope, making, equivalent method and scheme by claim definition contained in the present invention.Further, the present invention is had a better understanding in order to make the public, in hereinafter details of the present invention being described, detailed some specific detail sections of having described.There is not the description of these detail sections can understand the present invention fully for a person skilled in the art yet.
With reference to figure 1, be depicted as the flow chart of the fall detection method of the embodiment of the invention, may further comprise the steps:
S10 obtains the corresponding 3-axis acceleration analogue signal g of human body from 3-axis acceleration sensor
x, g
yAnd g
z, use peaceful filtering of the filtering algorithm Chinese and moving average method to carry out filtering and reduce the violent error deviation of moment that noise produces, the 3-axis acceleration digital signal that obtains is changed into comprehensive accekeration g;
Comprehensive accekeration g can obtain through formula 1:
S20 utilizes the comprehensive accekeration g obtain that the static original state of gravitational cue is calibrated, and utilizes integration to obtain to move both vertically velocity amplitude v1 and non-rotating state velocity amplitude v2;
The value of v1 and v2 has been represented move both vertically velocity amplitude and the non-rotating state velocity amplitude of having considered slightly to rock variable condition (as shaking hands) of only considering ultra weightlessness respectively.V1 error under the very big situation of g value is very big, so formula 2 retrains its positive, v2 then is that error amount is very big in rotation, but these two speed can produce Errors Catastrophic hardly simultaneously in same action.
S30, whether the instant value g that judges said comprehensive accekeration is less than setting threshold g
Th,
If be not less than setting threshold, return and continue S10,
If less than setting threshold, the integration that adds up obtains the difference of non-rotating state velocity amplitude and the said velocity amplitude that moves both vertically, and the moment point of the conditional judgment of falling is basically satisfied in the zero-time representative of integration, stops moment representative and adds up the finish time, gets into S40;
Constantly be the process of falling in the 23rd second to 26 seconds among Fig. 1, it is poor to find out significantly from figure that in this process v1 and v2 exist obvious speed, so the Δ v value C of an amplification of embodiment of the invention introducing.Difference DELTA v (the Δ v=Δ of the non-rotating state velocity amplitude v1 and the velocity amplitude v2 that moves both vertically
V1, v2=v1-v2); Carry out integral and calculating, the method for designing of speed difference has been simplified the sensitivity adjusting to algorithm, such as in the actual test of common sensitivity, only using v2; Two parameters of g are just enough; Threshold value that so only need v1 is set on the occasion of then ignoring this parameter, again because Δ v fix, has just directly confirmed v2 as long as confirmed v1 so.
T in the formula 4
0Represent this moment point that satisfies the conditional judgment of falling basically, just comprehensive acceleration g value is less than threshold value g
ThMoment point.T is representing the finish time of adding up, and is t in the present embodiment
0+ 3 seconds constantly.C is exactly the Δ v value that is exaggerated, and substitutes the value that Δ v value is carried out threshold decision.
Carry out the scope that threshold decision can be amplified threshold decision significantly with the C value, improve the accuracy of judging.Meanwhile; As can be seen from Figure 2 v1 does not have too big undulating value in this 3 second time; According to the test of many times signal analysis, v1 can't produce too big undulating value in the process of falling, even produce undulating value; C value after also can being exaggerated is ignored, so utilize the C value just can dispense the threshold decision of Δ v and v1 as threshold decision.Utilize this to improve one's methods and when improving accuracy of detection, can omit the number of threshold decision again.
Whether S40 judges difference that said accumulation calculating non-rotating state velocity amplitude and said integration obtain the velocity amplitude that moves both vertically less than setting threshold,
If less than setting threshold, return and continue S10,
If be not less than setting threshold, the difference of comprehensive accekeration of accumulation calculating and comprehensive acceleration of last moment gets into S50 as exercise intensity sign Δ G;
After preliminary testing conditions satisfies, then get into screening and judge, in 3 times in second after the Preliminary detection condition satisfies exercise intensity is calculated.Exercise intensity formula 5 integral representations capable of using:
What Δ G represented is comprehensive acceleration change value integration summation in 3 times in second, just a value that is used for weighing comprehensive acceleration change degree in 3 seconds.g
LastThe representative integration step pitch integration last time the time the g value.Comprehensive accekeration g should level off to g after falling under the normal condition
0(g
0=1), the human body value constantly that is not kept in motion just.Note g and standard gravity value g in the embodiment of the invention
0Difference be Δ g.This strength calculation method has considered that the weightless violent Gravity changer that produces with impact is arranged when falling.
Utilize Δ g and Δ G algorithm to carry out threshold decision in the last moment (finish times in 3 seconds) of exercise intensity screening conditions.When | Δ g| and Δ G can assert that this moment human body remains static respectively less than two corresponding threshold values the time, have the very big probability of falling.Otherwise, when | time explanation human body is also in motion not respectively less than threshold value for Δ g| and Δ G, and screening is not passed through.It is special here to exist | the situation that Δ g| and Δ G do not fall again less than threshold value respectively really, can assert to also have free active ability after human body is fallen, and therefore there is not necessity of early warning.
Whether step 50, the difference of judging the last comprehensive accekeration and comprehensive acceleration of last moment greater than setting threshold,
If greater than setting threshold, return and continue step 10,
If less than setting threshold, whether detect the exercise intensity sign greater than setting threshold, if less than setting threshold, get into step 60;
Whether step 70 judges the unspecified angle skew that calculates greater than the setting offset threshold,
If greater than setting offset threshold, return and continue step 10,
If less than setting offset threshold, do not exist three angles simultaneously less than the moment of threshold value and do not have comprehensive accekeration in the cycle time very first time with the difference of comprehensive acceleration of last moment is not more than its threshold value, the judgement human body is fallen.
Though the debug that exercise intensity screening can be to a great extent, hands is done long-time stop after the motion in the scope to a certain degree still possibly trigger erroneous judgement.For fear of this wrong the generation, the present invention introduces the angle conditional judgment again after above-mentioned Rule of judgment.
The angle calculation formula is difficult to calculate when overweight and weightlessness, but utilizes the ratio of following three gravity value of resting state and standard gravity value to be easy to draw the angle value of certain precision:
Formula 6 can obtain three deviation angle θ
x, θ
y, θ
z, simultaneously the default value of three deviation angles is 0, and setting gets well to be in three angle values and can use same threshold value to judge like this.So system can judge when existing wherein any angle greater than some threshold values in three angles and satisfies condition, and utilizes this condition can get rid of above-mentioned special circumstances.But the not all situation of angle calculation can be used, and have only to exist the kinestate angle just to have very big error, so the precondition that angle is judged is that human body has been in immobilized relatively state.
Even Preliminary detection, intensity and posture condition all satisfy; Can not get rid of the existence of the false positive incident of a large amount of special circumstances; For example the old people does stretching morning; Have certain probability to satisfy the Preliminary detection condition, the old man finishes subordinate a slip and hands is placed on chest static (angle is greater than certain value) after doing and then can gets into early warning.Therefore algorithm combines the time in 40 seconds to screen judgement again, as long as do not exist three angles in 40 times in second simultaneously less than the moment of threshold value and do not exist | and Δ g| is not more than under the situation of its threshold value and confirms that the situation of falling takes place.
Next describe the embodiment of the fall detection device corresponding in detail with fall detection method of the present invention.
Referring to Fig. 3; Fall detection apparatus structure sketch map for the embodiment of the invention; Comprise 3-axis acceleration sensor 10, move both vertically velocity amplitude and non-rotating state velocity amplitude acquisition module 20, first judge module 30, second judge module 40, the 3rd judge module 50, angular deflection acquisition module 60 and the 4th judge module 70
3-axis acceleration sensor 10 is used to obtain the corresponding 3-axis acceleration analogue signal of human body; Use peaceful filtering of the filtering algorithm Chinese and moving average method to carry out filtering and reduce the violent error deviation of moment that noise produces, the 3-axis acceleration digital signal that obtains is changed into comprehensive accekeration;
Move both vertically velocity amplitude and non-rotating state velocity amplitude acquisition module 20 is used to utilize the comprehensive accekeration that obtains that the static original state of gravitational cue is calibrated, and utilizes integration to obtain to move both vertically velocity amplitude and non-rotating state velocity amplitude;
Whether the instant value that first judge module 30 is used to judge said comprehensive accekeration less than setting threshold,
If be not less than setting threshold, return and continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If less than setting threshold, accumulation calculating non-rotating state velocity amplitude and said integration obtain the difference of the velocity amplitude that moves both vertically, and the moment point of the conditional judgment of falling is basically satisfied in the zero-time representative of integration, and stopping constantly, representative adds up the finish time;
Whether second judge module 40 is used to judge difference that said accumulation calculating non-rotating state velocity amplitude and said integration obtain the velocity amplitude that moves both vertically less than setting threshold,
If less than setting threshold, return and continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If be not less than setting threshold, the difference of comprehensive accekeration of accumulation calculating and comprehensive acceleration of last moment identifies as exercise intensity;
Whether the 3rd judge module 50 is used to judge the difference of the last comprehensive accekeration and comprehensive acceleration of last moment greater than setting threshold,
If greater than setting threshold, continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If less than setting threshold, whether detect the exercise intensity sign greater than setting threshold;
Angular deflection acquisition module 60 is used to calculate three angular deflection
Whether the 4th judge module 70 is used to judge the unspecified angle skew that calculates greater than the setting offset threshold,
If continue to obtain the corresponding 3-axis acceleration analogue signal of human body greater than setting offset threshold, returning,
If less than setting offset threshold, do not exist three angles simultaneously less than the moment of threshold value and do not have comprehensive accekeration in the cycle time very first time with the difference of comprehensive acceleration of last moment is not more than its threshold value, the judgement human body is fallen.
The purpose of the embodiment of the invention is the generation of comprehensive as much as possible false negative incident and false positive incident, and very high warning accuracy rate is arranged again simultaneously.The fall detection device of the embodiment of the invention adopts the threshold criteria of table 1, obtains the experimental data of table 2.
Table 1 threshold setting table
Table 2 experimental record table
Experimental result in the form 3 is that test obtains according to the threshold setting in the form 4.The embodiment of the invention action of will falling is divided into the front, rear, left and right four direction and does ten times respectively and fall.Forward direction is fallen and can both early warning be come out basically, but because hand still exists the case of not reporting to the police to the condition protective effect on ground.The back is relatively complicated to the action of falling, and hands possibly raise up and fall then, also exists bigger probability of false negative to a certain extent to falling after also possibly reducing buffering institute down, but utilizes the method judgement of C value can largely improve the buttock precision.In like manner fall because instrument is worn on the right hand in the left side, and the distance of fall of falling and impulsive force are limited and exist bigger probability of false negative equally, and still also the threshold decision through C has largely improved precision.But the easy large impact power that forms makes the C value have a large amount of minimizings of moment to produce very mistake in falling thereby fall in the right side, thus the precise decreasing that causes the right side to be fallen.Above-mentioned most false negative case probability of happening all can effectively be improved through changing each threshold value.
In another embodiment, a kind of wrist formula equipment is worn on the human body wrist place, comprises above-mentioned fall detection device.
The above is merely preferred embodiment of the present invention, not in order to restriction the present invention, all any modifications of within spirit of the present invention and principle, being done, is equal to and replaces and improvement etc., all should be included within protection scope of the present invention.
Claims (3)
1. a fall detection method is characterized in that, may further comprise the steps:
Step 10; Obtain the corresponding 3-axis acceleration analogue signal of human body from 3-axis acceleration sensor; Use peaceful filtering of the filtering algorithm Chinese and moving average method to carry out filtering and reduce the violent error deviation of moment that noise produces; The 3-axis acceleration digital signal that obtains is changed into comprehensive accekeration, get into step 20;
Step 20 utilizes the comprehensive accekeration obtain that the static original state of gravitational cue is calibrated, and utilizes integration to obtain to move both vertically velocity amplitude and non-rotating state velocity amplitude, entering step 30;
Whether step 30, the instant value of judging said comprehensive accekeration less than setting threshold,
If be not less than setting threshold, return and continue step 10,
If less than setting threshold, accumulation calculating non-rotating state velocity amplitude and said integration obtain the difference of the velocity amplitude that moves both vertically, and the moment point of the conditional judgment of falling is basically satisfied in the zero-time representative of integration, stop moment representative and add up the finish time, get into step 40;
Whether step 40 judges difference that said accumulation calculating non-rotating state velocity amplitude and said integration obtain the velocity amplitude that moves both vertically less than setting threshold,
If less than setting threshold, return and continue step 10,
If be not less than setting threshold, the difference of comprehensive accekeration of accumulation calculating and comprehensive acceleration of last moment identifies as exercise intensity, gets into step 50;
Whether step 50, the difference of judging the last comprehensive accekeration and comprehensive acceleration of last moment greater than setting threshold,
If greater than setting threshold, return and continue step 10,
If less than setting threshold, whether detect the exercise intensity sign greater than setting threshold, if less than setting threshold, get into step 60;
Step 60 is calculated three angular deflection, gets into step 70;
Whether step 70 judges the unspecified angle skew that calculates greater than the setting offset threshold,
If greater than setting offset threshold, return and continue step 10,
If less than setting offset threshold, do not exist three angles simultaneously less than the moment of threshold value and do not have comprehensive accekeration in the cycle time very first time with the difference of comprehensive acceleration of last moment is not more than its threshold value, the judgement human body is fallen.
2. fall detection device; It is characterized in that; Comprise 3-axis acceleration sensor, velocity amplitude and non-rotating state velocity amplitude acquisition module, first judge module, second judge module, the 3rd judge module, angular deflection acquisition module and the 4th judge module move both vertically
Said 3-axis acceleration sensor is used to obtain the corresponding 3-axis acceleration analogue signal of human body; Use peaceful filtering of the filtering algorithm Chinese and moving average method to carry out filtering and reduce the violent error deviation of moment that noise produces, the 3-axis acceleration digital signal that obtains is changed into comprehensive accekeration;
Said velocity amplitude and the non-rotating state velocity amplitude acquisition module of moving both vertically is used to utilize the comprehensive accekeration that obtains that the static original state of gravitational cue is calibrated, and utilizes integration to obtain to move both vertically velocity amplitude and non-rotating state velocity amplitude;
Whether the instant value that said first judge module is used to judge said comprehensive accekeration less than setting threshold,
If be not less than setting threshold, return and continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If less than setting threshold, accumulation calculating non-rotating state velocity amplitude and said integration obtain the difference of the velocity amplitude that moves both vertically, and the moment point of the conditional judgment of falling is basically satisfied in the zero-time representative of integration, and stopping constantly, representative adds up the finish time;
Whether said second judge module is used to judge difference that said accumulation calculating non-rotating state velocity amplitude and said integration obtain the velocity amplitude that moves both vertically less than setting threshold,
If less than setting threshold, return and continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If be not less than setting threshold, the difference of comprehensive accekeration of accumulation calculating and comprehensive acceleration of last moment identifies as exercise intensity;
Whether said the 3rd judge module is used to judge the difference of the last comprehensive accekeration and comprehensive acceleration of last moment greater than setting threshold,
If greater than setting threshold, continue to obtain the corresponding 3-axis acceleration analogue signal of human body,
If less than setting threshold, whether detect the exercise intensity sign greater than setting threshold;
Said angular deflection acquisition module is used to calculate three angular deflection
Whether said the 4th judge module is used to judge the unspecified angle skew that calculates greater than the setting offset threshold,
If continue to obtain the corresponding 3-axis acceleration analogue signal of human body greater than setting offset threshold, returning,
If less than setting offset threshold, do not exist three angles simultaneously less than the moment of threshold value and do not have comprehensive accekeration in the cycle time very first time with the difference of comprehensive acceleration of last moment is not more than its threshold value, the judgement human body is fallen.
3. a wrist formula equipment is worn on the human body wrist place, it is characterized in that, comprises power 2 described fall detection devices.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101334477A CN102657533B (en) | 2012-04-28 | 2012-04-28 | Falling detection method, falling detection device and wrist type device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101334477A CN102657533B (en) | 2012-04-28 | 2012-04-28 | Falling detection method, falling detection device and wrist type device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102657533A true CN102657533A (en) | 2012-09-12 |
| CN102657533B CN102657533B (en) | 2013-11-13 |
Family
ID=46767207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101334477A Expired - Fee Related CN102657533B (en) | 2012-04-28 | 2012-04-28 | Falling detection method, falling detection device and wrist type device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102657533B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577836A (en) * | 2013-09-30 | 2014-02-12 | 吴家宝 | Method and model system for establishing human body tumbling detection model |
| CN103581852A (en) * | 2013-09-30 | 2014-02-12 | 吴家宝 | Human body tumbling detection method and device and mobile terminal system |
| CN104408876A (en) * | 2014-12-10 | 2015-03-11 | 范子成 | Method and device for detecting and warning falling from high place |
| CN105212941A (en) * | 2015-08-25 | 2016-01-06 | 武汉理工大学 | A kind of human body active state recognition methods and system |
| CN105342626A (en) * | 2015-12-08 | 2016-02-24 | 成都麦杰康科技有限公司 | Wearable device and falling detection method applied to wearable device |
| CN105534501A (en) * | 2016-01-30 | 2016-05-04 | 深圳市易特科信息技术有限公司 | Sick-person or wounded-person rescuing system and method based on intelligent watch |
| CN105911310A (en) * | 2016-04-27 | 2016-08-31 | 广州市香港科大霍英东研究院 | A method and apparatus for detecting motion pattern of a user |
| CN105913614A (en) * | 2016-05-12 | 2016-08-31 | 上海海漾软件技术有限公司 | Method and device of monitoring tumbling, intelligent wearable device and tumbling alarm system |
| CN106023517A (en) * | 2016-05-24 | 2016-10-12 | 北京金坤科创技术有限公司 | High-altitude fall detecting and alarming method |
| CN106227999A (en) * | 2016-07-16 | 2016-12-14 | 北京工业大学 | A kind of high-adaptability is fallen behavioral value method |
| CN107569234A (en) * | 2017-09-06 | 2018-01-12 | 南京邮电大学 | A kind of fall detection algorithm based on Wrist belt-type equipment |
| CN108734921A (en) * | 2018-03-30 | 2018-11-02 | 北京医健保健康管理有限公司 | Fall detection algorithm and its detection device |
| CN108836352A (en) * | 2018-07-05 | 2018-11-20 | 京东方科技集团股份有限公司 | Tumble-preventing device and intelligent wearable device |
| CN109068006A (en) * | 2018-09-29 | 2018-12-21 | Oppo广东移动通信有限公司 | Fall the method reported, relevant device and storage medium |
| CN111547403A (en) * | 2020-04-27 | 2020-08-18 | 成都小步创想慧联科技有限公司 | Dumping state detection method and device for garbage can |
| CN112472075A (en) * | 2020-12-21 | 2021-03-12 | 福州数据技术研究院有限公司 | Fall detection method and system and storage device |
| CN113450539A (en) * | 2021-07-12 | 2021-09-28 | 杭州电子科技大学 | Fall detection method |
| CN113448293A (en) * | 2020-03-25 | 2021-09-28 | 精工爱普生株式会社 | Plant monitoring system |
| US11379047B2 (en) | 2019-06-25 | 2022-07-05 | Lifeline Systems Company | Evaluating movement of a subject |
| US11520410B2 (en) | 2019-06-25 | 2022-12-06 | Koninklijke Philips N.V. | Evaluating movement of a subject |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008129451A1 (en) * | 2007-04-19 | 2008-10-30 | Koninklijke Philips Electronics N.V. | Fall detection system |
| WO2010023604A1 (en) * | 2008-08-28 | 2010-03-04 | Koninklijke Philips Electronics N.V. | Fall detection and/or prevention systems |
| WO2010061321A1 (en) * | 2008-11-28 | 2010-06-03 | Koninklijke Philips Electronics N.V. | Method and apparatus for fall detection |
| US20110144542A1 (en) * | 2008-05-12 | 2011-06-16 | Koninklijke Philips Electronics N.V. | Displacement measurement in a fall detection system |
| CN102246216A (en) * | 2008-12-15 | 2011-11-16 | 皇家飞利浦电子股份有限公司 | Method and apparatus for calibrating a fall detector |
-
2012
- 2012-04-28 CN CN2012101334477A patent/CN102657533B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008129451A1 (en) * | 2007-04-19 | 2008-10-30 | Koninklijke Philips Electronics N.V. | Fall detection system |
| US20110144542A1 (en) * | 2008-05-12 | 2011-06-16 | Koninklijke Philips Electronics N.V. | Displacement measurement in a fall detection system |
| WO2010023604A1 (en) * | 2008-08-28 | 2010-03-04 | Koninklijke Philips Electronics N.V. | Fall detection and/or prevention systems |
| CN102132331A (en) * | 2008-08-28 | 2011-07-20 | 皇家飞利浦电子股份有限公司 | Fall detection and/or prevention system |
| WO2010061321A1 (en) * | 2008-11-28 | 2010-06-03 | Koninklijke Philips Electronics N.V. | Method and apparatus for fall detection |
| CN102246216A (en) * | 2008-12-15 | 2011-11-16 | 皇家飞利浦电子股份有限公司 | Method and apparatus for calibrating a fall detector |
Non-Patent Citations (3)
| Title |
|---|
| 张爱华等: "基于三维加速度传感器设计的跌倒检测", 《中国组织工程研究与临床康复》 * |
| 李冬等: "基于加速度传感器的老年人跌倒检测装置设计", 《传感器与微系统》 * |
| 郑立等: "人体跌倒监测方法及装置设计", 《中国医疗器械杂志》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577836B (en) * | 2013-09-30 | 2018-01-23 | 吴家宝 | Falling over of human body detection model method for building up and model system |
| CN103581852A (en) * | 2013-09-30 | 2014-02-12 | 吴家宝 | Human body tumbling detection method and device and mobile terminal system |
| CN103577836A (en) * | 2013-09-30 | 2014-02-12 | 吴家宝 | Method and model system for establishing human body tumbling detection model |
| CN103581852B (en) * | 2013-09-30 | 2018-03-06 | 吴家宝 | The method, device and mobile terminal system of falling over of human body detection |
| CN104408876A (en) * | 2014-12-10 | 2015-03-11 | 范子成 | Method and device for detecting and warning falling from high place |
| CN105212941A (en) * | 2015-08-25 | 2016-01-06 | 武汉理工大学 | A kind of human body active state recognition methods and system |
| CN105212941B (en) * | 2015-08-25 | 2017-12-29 | 武汉理工大学 | A kind of human body active state recognition methods and system |
| CN105342626A (en) * | 2015-12-08 | 2016-02-24 | 成都麦杰康科技有限公司 | Wearable device and falling detection method applied to wearable device |
| CN105342626B (en) * | 2015-12-08 | 2018-06-29 | 成都麦杰康科技有限公司 | Wearable and the fall detection method applied to Wearable |
| CN105534501A (en) * | 2016-01-30 | 2016-05-04 | 深圳市易特科信息技术有限公司 | Sick-person or wounded-person rescuing system and method based on intelligent watch |
| CN105911310A (en) * | 2016-04-27 | 2016-08-31 | 广州市香港科大霍英东研究院 | A method and apparatus for detecting motion pattern of a user |
| CN105911310B (en) * | 2016-04-27 | 2020-06-09 | 广州市香港科大霍英东研究院 | User motion mode detection method and device |
| CN105913614A (en) * | 2016-05-12 | 2016-08-31 | 上海海漾软件技术有限公司 | Method and device of monitoring tumbling, intelligent wearable device and tumbling alarm system |
| CN106023517A (en) * | 2016-05-24 | 2016-10-12 | 北京金坤科创技术有限公司 | High-altitude fall detecting and alarming method |
| CN106227999A (en) * | 2016-07-16 | 2016-12-14 | 北京工业大学 | A kind of high-adaptability is fallen behavioral value method |
| CN106227999B (en) * | 2016-07-16 | 2018-10-09 | 北京工业大学 | A kind of high-adaptability tumble behavioral value method |
| CN107569234A (en) * | 2017-09-06 | 2018-01-12 | 南京邮电大学 | A kind of fall detection algorithm based on Wrist belt-type equipment |
| CN108734921A (en) * | 2018-03-30 | 2018-11-02 | 北京医健保健康管理有限公司 | Fall detection algorithm and its detection device |
| CN108836352A (en) * | 2018-07-05 | 2018-11-20 | 京东方科技集团股份有限公司 | Tumble-preventing device and intelligent wearable device |
| CN108836352B (en) * | 2018-07-05 | 2021-02-02 | 京东方科技集团股份有限公司 | Prevent falling down device and intelligent wearing equipment |
| CN109068006A (en) * | 2018-09-29 | 2018-12-21 | Oppo广东移动通信有限公司 | Fall the method reported, relevant device and storage medium |
| US11379047B2 (en) | 2019-06-25 | 2022-07-05 | Lifeline Systems Company | Evaluating movement of a subject |
| US11520410B2 (en) | 2019-06-25 | 2022-12-06 | Koninklijke Philips N.V. | Evaluating movement of a subject |
| CN113448293A (en) * | 2020-03-25 | 2021-09-28 | 精工爱普生株式会社 | Plant monitoring system |
| CN113448293B (en) * | 2020-03-25 | 2024-03-22 | 精工爱普生株式会社 | Plant monitoring system |
| CN111547403A (en) * | 2020-04-27 | 2020-08-18 | 成都小步创想慧联科技有限公司 | Dumping state detection method and device for garbage can |
| CN112472075A (en) * | 2020-12-21 | 2021-03-12 | 福州数据技术研究院有限公司 | Fall detection method and system and storage device |
| CN113450539A (en) * | 2021-07-12 | 2021-09-28 | 杭州电子科技大学 | Fall detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102657533B (en) | 2013-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102657533B (en) | Falling detection method, falling detection device and wrist type device | |
| Purwar et al. | Activity monitoring from real-time triaxial accelerometer data using sensor network | |
| CN103027687B (en) | Old people fall detection and alarm system based on 3D (3-dimensional) accelerometer and gyroscope | |
| CN102667882B (en) | Method and device for detecting falls by users | |
| CN102227189B (en) | Method and apparatus for fall detection | |
| CN103680063B (en) | Based on mobile phone accelerometer and gyrostatic old person abnormal condition decision method | |
| CN101969848A (en) | An activity monitoring system insensitive to accelerations induced by external motion factors | |
| JP2012105762A5 (en) | ||
| CN102368297A (en) | Equipment, system and method for recognizing actions of detected object | |
| Hsieh et al. | A wrist-worn fall detection system using accelerometers and gyroscopes | |
| CN104932674B (en) | Impulse detection circuit, measuring physical, electronic equipment and moving body | |
| CN103768775B (en) | Based on the method for counting of the rope skipping counting device of 3-axis acceleration | |
| Chen et al. | A wireless real-time fall detecting system based on barometer and accelerometer | |
| CN103557862A (en) | Detection method for movement track of mobile terminal | |
| CN203025989U (en) | Musical instrument simulation training and evaluation system based on action recognition | |
| CN104535032A (en) | Vertical jump height measuring method and device based on mobile terminal gravity sensor | |
| CN101975582A (en) | Personnel motion trail tracking method and device | |
| Xie et al. | ART: adaptive and real-time fall detection using COTS smart watch | |
| KR101189667B1 (en) | Apparatus and method for measuring surpluscalories using acceleration sensor | |
| CN105551191A (en) | Falling detection method | |
| CN105448039A (en) | Tumble-detecting method decreasing false alarm rate | |
| CN114341947A (en) | System and method for exercise type recognition using wearable devices | |
| Liu et al. | Preimpact fall detection for elderly based on fractional domain | |
| CN106767800B (en) | A kind of paces segmentation detection method | |
| CN204576953U (en) | A kind of artificial manufacture earthquake simulation demonstrating apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20131113 |